R Data structure Vector, Matrix, List, DataFrame

4 ต.ค. 2023 , 737 Views , หมวดหมู่ R Programming โค๊ดดิ้ง , ป้ายกำกับ:DataFrame, List, Matrix, R Data structure, Vector

Vector — เก็บข้อมูลได้ 1 data type

หนึ่ง Vector เก็บข้อมูลได้แค่ 1 ประเภท

1:10
# 1  2  3  4  5  6  7  8  9 10

16:25
#16 17 18 19 20 21 22 23 24 25

## sequence generation
seq(from = 1, to = 100, by = 5)
# 1  6 11 16 21 26 31 36 41 46 51 56 61 66 71 76 81 86 91 96

## help file
help("seq")

## function c
friends <- c("Daviid", "Marry", "Anna", "John", "William")
ages <- c(20, 35, 43, 18, 27)
is_mail <- c(TRUE, FALSE, FALSE, TRUE, TRUE)

print(friends); print(ages); print(is_mail)
# "Daviid"  "Marry"   "Anna"    "John"    "William"
# 20 35 43 18 27
# TRUE FALSE FALSE  TRUE  TRUE

1:10

# 1 2 3 4 5 6 7 8 9 10

16:25

#16 17 18 19 20 21 22 23 24 25

## sequence generation

seq(from = 1, to = 100, by = 5)

# 1 6 11 16 21 26 31 36 41 46 51 56 61 66 71 76 81 86 91 96

## help file

help("seq")

## function c

friends <- c("Daviid", "Marry", "Anna", "John", "William")

ages <- c(20, 35, 43, 18, 27)

is_mail <- c(TRUE, FALSE, FALSE, TRUE, TRUE)

print(friends); print(ages); print(is_mail)

# "Daviid" "Marry" "Anna" "John" "William"

# 20 35 43 18 27

# TRUE FALSE FALSE TRUE TRUE

…

## vector
friends <- c("Nathan","Koy","Gle","King")
length(friends) #เชคความยาว

#เข้าไปดึงค่าใน obj นั้นขึ้นมา
friends[1] 
# "Nathan"
friends[3:5]
# "Gle"  "King" NA
friends[c(1,3,4)]
# "Nathan" "Gle"    "King"

#เปลี่ยนค่าใหม่
friends[1] <- "Ditto" 
friends
# "Ditto" "Koy"   "Gle"   "King"
friends[1:2] <- c("A","B")
friends
# "A"    "B"    "Gle"  "King"

## หาตำแหน่ง index
which(friends == "Gle")
# 3

## vector

friends <- c("Nathan","Koy","Gle","King")

length(friends) #เชคความยาว

#เข้าไปดึงค่าใน obj นั้นขึ้นมา

friends[1]

# "Nathan"

friends[3:5]

# "Gle" "King" NA

friends[c(1,3,4)]

# "Nathan" "Gle" "King"

#เปลี่ยนค่าใหม่

friends[1] <- "Ditto"

friends

# "Ditto" "Koy" "Gle" "King"

friends[1:2] <- c("A","B")

friends

# "A" "B" "Gle" "King"

## หาตำแหน่ง index

which(friends == "Gle")

# 3

Matrix

เก็บข้อมูลได้ 1 ประเภท แต่จะมี 2 dimension คือ column และ row สร้าง Matrix ด้วยคำสั่ง matrix()

m <- matrix(1:10, ncol = 2)
m
# 		[,1] [,2]
# [1,]    1    6
# [2,]    2    7
# [3,]    3    8
# [4,]    4    9
# [5,]    5   10

m <- matrix(1:10, ncol = 2, byrow = TRUE)
m
# 		[,1] [,2]
# [1,]    1    2
# [2,]    3    4
# [3,]    5    6
# [4,]    7    8
# [5,]    9   10

## element wise computation
m*2
# 		[,1] [,2] [,3] [,4] [,5]
# [1,]    2    4    6    8   10
# [2,]   12   14   16   18   20
# [3,]   22   24   26   28   30
# [4,]   32   34   36   38   40

m <- matrix(c(1,2,3), ncol = 2)
y <- matrix(c(4,5,6), ncol = 2)
m*y
# 		[,1] [,2]
# [1,]    4   18
# [2,]   10    4

y <- 1:6
dim(y) <- c(3,2)
y
# 		[,1] [,2]
# [1,]    1    4
# [2,]    2    5
# [3,]    3    6

m <- matrix(1:10, ncol = 2)

# [,1] [,2]

# [1,] 1 6

# [2,] 2 7

# [3,] 3 8

# [4,] 4 9

# [5,] 5 10

m <- matrix(1:10, ncol = 2, byrow = TRUE)

# [,1] [,2]

# [1,] 1 2

# [2,] 3 4

# [3,] 5 6

# [4,] 7 8

# [5,] 9 10

## element wise computation

m*2

# [,1] [,2] [,3] [,4] [,5]

# [1,] 2 4 6 8 10

# [2,] 12 14 16 18 20

# [3,] 22 24 26 28 30

# [4,] 32 34 36 38 40

m <- matrix(c(1,2,3), ncol = 2)

y <- matrix(c(4,5,6), ncol = 2)

m*y

# [,1] [,2]

# [1,] 4 18

# [2,] 10 4

y <- 1:6

dim(y) <- c(3,2)

# [,1] [,2]

# [1,] 1 4

# [2,] 2 5

# [3,] 3 6

List — เก็บได้หลาย data type

เก็บข้อมูลแบบ key = value
เก็บข้อมูลได้หลากหลายประเภท สร้าง List ด้วยคำสั่ง list()

my_playlist <- list(
  fav_movie = "The Dark Knight",
  fav_song = "OMG",
  fav_artist = "NewJeans"
)

my_playlist$fav_movie
# "The Dark Knight"

my_playlist[1]
# $fav_movie
# "The Dark Knight"

my_playlist[[1]]
# "The Dark Knight"

my_playlist <- list(
  fav_movie = c("The Dark Knight","Marvel"),
  fav_song = c("OMG","XX"),
  fav_artist = "NewJeans"
)
my_playlist$fav_movie[2]
my_playlist[[1]][2]
# "Marvel"

## customer database for our company
customer_01 <- list(
  name = "Nathan",
  location = "BKK",
  age = 38,
  movies = c("John Wick", "Dark Knight")
)

customre_02 <- list(
  name = "moh",
  lname = "wick",
  age = 42,
  movies = "john Wick 4",
  fav_weapon = "A Pencil"
)

customer_db <- list(
  nathan = customer_01,
  moh = customre_02
)
customer_db$nathan$name
# "Nathan"

## อยากรู้ key
names(customer_db)
# "nathan" "moh"

my_playlist <- list(

fav_movie = "The Dark Knight",

fav_song = "OMG",

fav_artist = "NewJeans"

)

my_playlist$fav_movie

# "The Dark Knight"

my_playlist[1]

# $fav_movie

# "The Dark Knight"

my_playlist[[1]]

# "The Dark Knight"

my_playlist <- list(

fav_movie = c("The Dark Knight","Marvel"),

fav_song = c("OMG","XX"),

fav_artist = "NewJeans"

)

my_playlist$fav_movie[2]

my_playlist[[1]][2]

# "Marvel"

## customer database for our company

customer_01 <- list(

name = "Nathan",

location = "BKK",

age = 38,

movies = c("John Wick", "Dark Knight")

)

customre_02 <- list(

name = "moh",

lname = "wick",

age = 42,

movies = "john Wick 4",

fav_weapon = "A Pencil"

)

customer_db <- list(

nathan = customer_01,

moh = customre_02

)

customer_db$nathan$name

# "Nathan"

## อยากรู้ key

names(customer_db)

# "nathan" "moh"

Data Frame

คือ Table นั่นเอง ความรู้เรื่อง Data Frame เป็นพื้นฐานสำคัญของ Data Analists งานของเรามากกว่า 80% ทำงานกับ structured data เช่น ข้อมูลใน Excel/ Google Sheets และที่เราดึงออกมาจาก SQL databases

สร้าง Data Frame ด้วย data.frame()
Create data frame จาก vector ซึ่ง vector ต้องมีความยาวเท่ากัน

#แสดงชื่อ build-in data frame
data()
mtcars #build-in data frame

## create data frame from vector
friends <- c("Nathan","Koy","gle","Kung","Noi")
ages <- c(37,32,7,0,6)
movie_lover <- c(T,F,T,F,T)

df <- data.frame(id = 1:5,
           friend=friends,
           age=ages,
           movie =movie_lover)
df
# 	id friend age movie
#	1  1 Nathan  37  TRUE
#	2  2    Koy  32 FALSE
#	3  3    gle   7  TRUE
#	4  4   Kung   0 FALSE
#	5  5    Noi   6  TRUE

# alterative approach to create data frame in R
customrers <- list(
  friends = c("John",NA),
  ages = c(23,45),
  movie = c(T,F)
)

df <- data.frame(customrers)
View(df)
## ตรวจสอบค่าว่าง
is.na(df)
## หาจำนวนค่า NA
sum(is.na(df))

## วิธีดึงข้อมูล
df$friends[2]
df[[1]][2]

## ดึงทุก row , coloumn 2:3
df[ ,2:3]

##ดึง row 1:3, ทุก column
df[1:3, ]

##
df[, c(1,3)]
df[ ,c("ages","friends")]

##
lisa_index <- which(df$friends == "John")
lisa_index
df[lisa_index, "friends"] <- "Nathannnnnnn"

## ดึงข้อมูลตามเงื่อนไข
df[df$age < 30, ]
df[!df$movie, ] #ดึง row ที่ไม่ชอบดูหนัง
 #ดึงหลายเงื่อนไข and (&) or (|)
condition <- !df$movie & df$ages > 30 #and
df[condition, ]

condition <- !df$movie | df$ages > 30 #or
df[condition, ]

#export เป็น csv
write.csv(df, "friends.csv", row.names = FALSE)

#read csv
df <- read.csv("friends.csv")

#แสดงชื่อ build-in data frame

data()

mtcars #build-in data frame

## create data frame from vector

friends <- c("Nathan","Koy","gle","Kung","Noi")

ages <- c(37,32,7,0,6)

movie_lover <- c(T,F,T,F,T)

df <- data.frame(id = 1:5,

friend=friends,

age=ages,

movie =movie_lover)

# id friend age movie

# 1 1 Nathan 37 TRUE

# 2 2 Koy 32 FALSE

# 3 3 gle 7 TRUE

# 4 4 Kung 0 FALSE

# 5 5 Noi 6 TRUE

# alterative approach to create data frame in R

customrers <- list(

friends = c("John",NA),

ages = c(23,45),

movie = c(T,F)

)

df <- data.frame(customrers)

View(df)

## ตรวจสอบค่าว่าง

is.na(df)

## หาจำนวนค่า NA

sum(is.na(df))

## วิธีดึงข้อมูล

df$friends[2]

df[[1]][2]

## ดึงทุก row , coloumn 2:3

df[ ,2:3]

##ดึง row 1:3, ทุก column

df[1:3, ]

df[, c(1,3)]

df[ ,c("ages","friends")]

lisa_index <- which(df$friends == "John")

lisa_index

df[lisa_index, "friends"] <- "Nathannnnnnn"

## ดึงข้อมูลตามเงื่อนไข

df[df$age < 30, ]

df[!df$movie, ] #ดึง row ที่ไม่ชอบดูหนัง

#ดึงหลายเงื่อนไข and (&) or (|)

condition <- !df$movie & df$ages > 30 #and

df[condition, ]

condition <- !df$movie | df$ages > 30 #or

df[condition, ]

#export เป็น csv

write.csv(df, "friends.csv", row.names = FALSE)

#read csv

df <- read.csv("friends.csv")

Subset

ดึงข้อมูลออกมาจาก Data structure Subset ด้วย Position, name, condition

ดึงจาก Vector

friends <- c("Daviid", "Marry", "Anna", "John", "William")
ages <- c(20, 35, 43, 18, 27)

## by position
friends[1]
# "Daviid"
friends[2]
# "Marry"
friends[1:4]
# "Daviid" "Marry"  "Anna"   "John"
friends[c(1,2,5)]
# "Daviid"  "Marry"   "William"

## by condition
ages[ages > 30]
# 35 43
ages[ages <= 30]
# 20 18 27

## by name ใช้ function names()
names(ages) <- friends
ages
# Daviid   Marry    Anna    John William 
#    20      35      43      18      27

ages["Marry"]
# Marry 
#    35 
ages[c("Marry", "Anna", "John")]
# Marry  Anna  John 
#    35    43    18

friends <- c("Daviid", "Marry", "Anna", "John", "William")

ages <- c(20, 35, 43, 18, 27)

## by position

friends[1]

# "Daviid"

friends[2]

# "Marry"

friends[1:4]

# "Daviid" "Marry" "Anna" "John"

friends[c(1,2,5)]

# "Daviid" "Marry" "William"

## by condition

ages[ages > 30]

# 35 43

ages[ages <= 30]

# 20 18 27

## by name ใช้ function names()

names(ages) <- friends

ages

# Daviid Marry Anna John William

# 20 35 43 18 27

ages["Marry"]

# Marry

# 35

ages[c("Marry", "Anna", "John")]

# Marry Anna John

# 35 43 18

ดึงจาก Data frame

## df[row, col]
## by position
df[1, 3]
# "Bangkok"
df[1:2, 4]
# TRUE TRUE
df[1:2, 2:4]
#   ages     location movie
# 1   20      Bangkok  TRUE
# 2   35 Mahasarakham  TRUE

## by name
df[ ,"friends"]
# "Daviid"  "Marry"   "Anna"    "John"    "William"

df[, c("friends", "location")]
#   friends     location
# 1  Daviid      Bangkok
# 2   Marry Mahasarakham
# 3    Anna        Surin
# 4    John      Konkean
# 5 William         Loei


## by condition ให้ใส่เงื่อนไขใน row
df[ df$friends=="Marry", ]
#   friends ages     location movie
# 2   Marry   35 Mahasarakham  TRUE

df [ df$movie==TRUE, c("friends", "ages", "movie")]
#   friends ages movie
# 1  Daviid   20  TRUE
# 2   Marry   35  TRUE
# 5 William   27  TRUE

df[ df$ages < 30, ]
#   friends ages location movie
# 1  Daviid   20  Bangkok  TRUE
# 4    John   18  Konkean FALSE
# 5 William   27     Loei  TRUE

## df[row, col]

## by position

df[1, 3]

# "Bangkok"

df[1:2, 4]

# TRUE TRUE

df[1:2, 2:4]

# ages location movie

# 1 20 Bangkok TRUE

# 2 35 Mahasarakham TRUE

## by name

df[ ,"friends"]

# "Daviid" "Marry" "Anna" "John" "William"

df[, c("friends", "location")]

# friends location

# 1 Daviid Bangkok

# 2 Marry Mahasarakham

# 3 Anna Surin

# 4 John Konkean

# 5 William Loei

## by condition ให้ใส่เงื่อนไขใน row

df[ df$friends=="Marry", ]

# friends ages location movie

# 2 Marry 35 Mahasarakham TRUE

df [ df$movie==TRUE, c("friends", "ages", "movie")]

# friends ages movie

# 1 Daviid 20 TRUE

# 2 Marry 35 TRUE

# 5 William 27 TRUE

df[ df$ages < 30, ]

# friends ages location movie

# 1 Daviid 20 Bangkok TRUE

# 4 John 18 Konkean FALSE

# 5 William 27 Loei TRUE

connect data source ผ่าน gateway error We were…

R Variable, Data types

ป้ายกำกับ:DataFrame, List, Matrix, R Data structure, Vector

หมวดหมู่

ติดต่อเรา

ติดตามเรา

R Data structure Vector, Matrix, List, DataFrame

Vector — เก็บข้อมูลได้ 1 data type

Matrix

List — เก็บได้หลาย data type

Data Frame

Subset

ดึงจาก Vector

ดึงจาก Data frame

Related Posts

หมวดหมู่

Popular Posts

ป้ายกำกับ

ติดต่อเรา

ติดตามเรา